Image inspection system

Abstract

An image inspection system that inspects an image recorded on a recording medium includes one or more hardware processors; and one or more memories storing one or more programs including instructions for storing a first trained model that is generated by machine learning based on learning recorded images that are images for machine learning, recorded on recording media, storing a second trained model that is generated by machine learning based on recording information that is different from the learning recorded images, acquiring a first probability of a defect being in an actual recorded image, acquiring a first estimation result, acquiring a second probability of a defect being in the actual recorded image; acquiring as a second estimation result and detecting a defect in the actual recorded image on the basis of the first estimation result and the second estimation result.

What is claimed is: 
     
         1 . An image inspection system inspecting an image recorded on a recording medium by a recording device, the image inspection system comprising:
 one or more hardware processors; and   one or more memories storing one or more programs configured to be executed by the one or more hardware processors, the one or more programs including instructions for:   storing a first trained model that is generated by machine learning based on learning recorded images that are images for machine learning, recorded on recording media;   storing a second trained model that is generated by machine learning based on recording information that is different from the learning recorded images and that is information relating to at least one of the recording device and the recording medium at a time of recording the learning recorded images;   acquiring a first probability of a defect being in an actual recorded image that is an object of inspection by the first trained model;   acquiring a first estimation result that is an evaluation result regarding whether the actual recorded image is normal or abnormal by a first estimating portion on the basis of the first probability;   acquiring a second probability of a defect being in the actual recorded image by the second trained model;   acquiring a second estimation result that is an evaluation result regarding whether the actual recorded image is normal or abnormal by a second estimating portion; and   detecting a defect in the actual recorded image on the basis of the first estimation result and the second estimation result.   
     
     
         2 . The image inspection system according to  claim 1 ,
 wherein in a case in which the first probability is no lower than a first threshold value, the first estimating portion sets the first estimation result to the effect that the actual recorded image has an abnormality, and in a case in which the second probability is no lower than a second threshold value, the second estimating portion sets the second estimation result to the effect that the actual recorded image has an abnormality.   
     
     
         3 . The image inspection system according to  claim 2 ,
 wherein the first threshold value and the second threshold value are 50%.   
     
     
         4 . The image inspection system according to  claim 1 ,
 wherein the first trained model is generated by machine learning based on the learning recorded images and an evaluation result regarding whether the learning recorded images are normal or abnormal, and   wherein the evaluation result is data in which a probability of a defect being in the actual recorded image is 100% in a case in which the recorded image is abnormal, and is data in which a probability of a defect being in the actual recorded image is 0% in a case in which the recorded image is normal.   
     
     
         5 . The image inspection system according to  claim 1 , further comprising:
 a data generating portion that divides image data acquired from the actual recorded image into a plurality and generates divided image data,   wherein the first estimating portion estimates whether each of the plurality of the divided image data is normal or abnormal, and acquires the first estimation result on the basis of the estimation results thereof.   
     
     
         6 . The image inspection system according to  claim 5 ,
 wherein the data generating portion divides the image data of the actual recorded image by a predetermined vertical width, a predetermined lateral width, and a predetermined shifting amount, and generates the divided image data.   
     
     
         7 . The image inspection system according to  claim 5 ,
 wherein, when it is determined that one or more pieces of the divided image data is abnormal, the first estimating portion decides that the first estimation result indicates that the actual recorded image has an abnormality.   
     
     
         8 . The image inspection system according to  claim 1 ,
 wherein the recording information includes at least one of ink concentration at a time of recording the image, environment temperature, environment humidity, thickness of an actual recording medium on which the actual recorded image is recorded, and coating type of the actual recording medium.   
     
     
         9 . The image inspection system according to  claim 1 ,
 wherein the recording information includes at least one of position information of a liquid discharge head that discharges liquid, which the recording device is equipped with, at a time of recording the image, count of times of cleaning a nozzle of the liquid discharge head, and a roller diameter of a roller making up a conveying path for the recording medium, which the recording device is equipped with.   
     
     
         10 . The image inspection system according to  claim 1 ,
 wherein the second estimating portion includes the recording information at a plurality of points in time at time of recording the image.   
     
     
         11 . The image inspection system according to  claim 10 ,
 wherein the second estimating portion estimates whether or not each of the recording information at the plurality of points in time is normal, and acquires the second estimation result on the basis of the estimation results thereof.   
     
     
         12 . The image inspection system according to  claim 11 ,
 wherein, when it is determined that one or more pieces of recording information of the recording information at the plurality of points in time is abnormal, the second estimating portion decides that the second estimation result is to the effect that the actual recorded image has an abnormality.   
     
     
         13 . The image inspection system according to  claim 1 ,
 wherein, when both the first estimation result and the second estimation result are determined to be abnormal, the image inspection system notifies a user that there is a defect in the actual recorded image.   
     
     
         14 . The image inspection system according to  claim 13 ,
 wherein, when there is a defect in the actual recorded image, the image inspection system notifies a user of a defect portion being present.   
     
     
         15 . The image inspection system according to  claim 1 ,
 wherein, when both the first estimation result and second estimation result is abnormal, recording operations being executed by the recording device are stopped.   
     
     
         16 . The image inspection system according to  claim 1 ,
 wherein, when the first estimation result is abnormal and the second estimation result is normal, or when the first estimation result is normal and the second estimation result is abnormal, the image inspection system notifies a user that a defect may be present in the actual recorded image.   
     
     
         17 . The image inspection system according to  claim 1 ,
 wherein, when the first estimation result is abnormal and the second estimation result is normal, the image inspection system notifies a user that a defect portion in the image data of the actual recorded is present.   
     
     
         18 . The image inspection system according to  claim 1 ,
 wherein, in a case in which the first estimation result is normal and the second estimation result is abnormal, the image inspection system notifies a user of information representing parameter data that contributes to the abnormal determination.   
     
     
         19 . The image inspection system according to  claim 1 ,
 wherein, when the first estimation result is abnormal, the second estimating portion acquires the second estimation result.